© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194860
    Prev
    Next
    INDEX
    Explanations

    following status or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    サート
    0.45
    дем
    0.44
    دين
    0.44
    y
    0.44
     moistened
    0.42
    ა
    0.42
    ινή
    0.41
    et
    0.41
    ων
    0.41
    ゛
    0.41
    POSITIVE LOGITS
     যত
    0.55
     adduct
    0.52
    ANG
    0.52
     seguente
    0.51
    槨
    0.50
    북
    0.49
     следующие
    0.48
     악
    0.47
     couldn
    0.47
    𝙋
    0.47
    Activations Density 0.000%

    No Known Activations